Statistical research and consulting in universities from developing countries: The Colombian case

Abstract

This paper focuses on describing the experience of statistical researchers and consultants of the Department of Mathematics and Statistics, faculty and students, and of researchers who are not statisticians, at the Universidad Nacional de Colombia. An analysis is made of the statistics programs of study including consulting activities, and of three surveys that were designed, distributed and analysed: one for the newly graduated and senior year students concerning their training in research and consulting during their studies; a second one for statistics staff at the department and a third for non-statistician researchers at the University who usually have to deal with statistical methods. A study is made of the main problems in the formation and training of students as statistical researchers and consultants, as well as the difficulties of the experienced researchers and consultants. Recommendations to improve the actual situation are proposed.

The statistical consultancy workshop as a pedagogical tool

“…The project of Statistical Consultancy Workshops and Units can serve as a meeting point for potential clients and suppliers of statistical consultancy and can follow the example of this type of consulting services in other countries (as in the examples discussed in Belli, 2001;Jolliffe, 2001, Ospina, 2001. This will allow students of experimental disciplines (humanities, social, sciences, technology) to appreciate the benefits of using statistics in a reasonable way.…”

Learning from experience

“…Teaching of consultancy, if to be effective, must attempt to give students practice in doing consultancy, for example, by having them sit in on or participate in consulting sessions (see Rangecroft, & Wallace, 1998), or by setting up consultancy situations based on real problems. See also Belli (2001), Godino et al (2001) and Ospina and Ortiz (2001) for discussion of training in consultancy. Ideally facilitators of training courses in consultancy should themselves have experience of acting as consultants, or at least have worked as practical statisticians, and, as Nelder (1986) comments, every statistician's training should involve collection and analysis of their own data -and that involves learning about the area of application.…”

The role of a research resource centre in the training of social science researchers

“…This inevitably involves using real rather than 'fake' data, an approach supported by a number of other statistics educators. For example, Hirotsu (2001), argues that it is essential to use actual problems to teach statistics, while Ospina and Ortiz (2001) support the use of real data to solve real problems as in the long run, this is important for statistics education. Similarly, Svensson (2001) encourages the use of the researchers' own research problems as a way of understanding methodological and statistical theories and has adopted an approach that focuses on statistical strategy rather than statistical technique.…”